Lecture 08 — Flex / Catch-up

Open lab: revisit whatever isn’t sticking yet

Bill Perry

2026-09-10

No New Material Today

This is a flex day. We use it to go back over whatever from Lectures 01–07 is not sticking yet — as a class, in small groups, or one-on-one while everyone else works ahead on the Wrangling / Summary Statistics extensions or gets a head start on Worksheet 07.

Tip

🖐 How today works

Bring your own script with whatever is broken or confusing. We will fix real code, not hypothetical examples.

Note

✅ Key idea

Getting stuck and asking about it today is cheaper than carrying a shaky foundation into Wrangling, Summary Statistics, and eventually t-tests.

What We’ve Covered So Far

#	Topic
01	Asking a question, designing the leaf study
02	Meeting R, Positron, and project structure
03	GGPlot I — colors, facets, `stat_summary()`
04	GGPlot II — more geoms, coordinates, themes
05	Wrangling — `filter`, `select`, `mutate`, `arrange`
06	Summary statistics — mean, SD, SE, `group_by()`
07	Quarto — reproducible reports

Note

📖 Where to look things up

common_code/ on the course site has a standalone reference page for every one of these topics
Each lecture’s References slide links the relevant Whitlock & Schluter and R4DS chapters

Self-Check — Can You Do These?

Load an Excel file with read_excel() and clean names with clean_names()
Explain what %>% does, out loud, in one sentence
Build a boxplot with jittered points, colored on purpose with scale_fill_manual()
Facet a plot with facet_wrap()
Chain filter(), select(), mutate(), arrange() into one pipeline
Compute mean, SD, and SE for a group — by hand and with group_by() + summarize()
Explain why sum(!is.na(x)) is safer than length(x)
Render a Quarto document that mixes prose, code, and a figure

Tip

🖐 If you checked fewer than 6 boxes

Start there today — with me, with a classmate, or with the worksheet for that lecture. That is exactly what this session is for.

Options for Today

Rebuild a worksheet from scratch, no peeking at the answer key, then compare
Trade scripts with a neighbor and try to explain what each line does
Re-run a lecture’s code chunks one at a time, predicting the output first
Get ahead: start Worksheet 07 (Quarto) or the Summary Statistics extension if you’re solid on everything above

Important

⚠️ Watch out!

“I understand it when I watch it” and “I can type it myself with no notes” are two different skills. Today is for practicing the second one.

Up Next — Lecture 09

Two-sample t-test: formally testing our sunny-vs-shady hypothesis
Checking assumptions (normality, equal variance)
Everything from Lectures 05–06 (wrangling and summary statistics) is a direct prerequisite — that is why today exists.